Abstract
We exploit the connection between boosting and greedy coordinate optimization to produce new accelerated boosting methods. Specifically, we look at increasing block sizes, better selection rules, and momentum-type acceleration. Numerical results show training convergence gains over several data sets. The code is made publicly available.
Xiaomeng Ju
Postdoctoral research fellow in Biostatistics
I am a postdoctoral research fellow in the Division of Biostatistics, at the New York University, Grossman School of Medicine. My research interests include functional data analysis, tensor modeling, and robust statistics. I am particularly interested in developing statistical tools for the analysis of neuroimaging data.